Does Athento support character recognition and auto-classification of documents?

Athento offers document capture and analysis functionality.

Athento is capable of analyzing numerous document characteristics such as predominant colors, histograms, OCR, HOCR, white analysis, text orientation, among other features.

Thanks to this analysis it is possible to automate tasks such as the automatic classification of documents, their organization and automatic categorization in document repositories or the extraction of data from their textual content.

Some of the functionality offered by the product in this regard is described below.

Document analysis:

• Text or image analysis mechanisms.
• Entity or object detection in images.
• Face detection in images.
• Histogram extraction.
• Extraction of the predominant colors in documents.
• Detection of the percentage of white on a page.

Data extraction:

• Document Text Extraction (OCR)
• Extraction of semantic tags from the document.
• Metadata extraction by coordinates.
• Metadata extraction by regular expressions.
• Extraction of barcodes and QR codes.
• Metadata extraction in tables.
• Metadata extraction by anchors (HOCR).

Export:

• Metadata export in Excel.
• Metadata export in XML.

Validation:

• Manual metadata validation via form.
• Automatic metadata validation via database connection.
• Syntactic validation of metadata.

Capture/load:

• Upload via monitored folders.
• Uploading by e-mail.
• Uploading through forms.
• API
• Public forms